Commit
•
09b67b1
1
Parent(s):
2f10607
Librarian Bot: Add base_model information to model (#1)
Browse files- Librarian Bot: Add base_model information to model (16475cae94ceeb561a1050f0824ab4c1e7ce73ac)
Co-authored-by: Librarian Bot (Bot) <librarian-bot@users.noreply.huggingface.co>
README.md
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
---
|
2 |
-
library_name: peft
|
3 |
-
license: cc-by-4.0
|
4 |
-
datasets:
|
5 |
-
- iamshnoo/alpaca-cleaned-bengali
|
6 |
language:
|
7 |
- bn
|
8 |
- en
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
This represents the PEFT weights only. The base model is LLaMA 2. Instruction finetuning was done using 4 bit QLoRA on a single A100 GPU with the PEFT config as given below. The dataset used for this instruction finetuning process is a translated version of the cleaned alpaca dataset (translated using NLLB-1.3B).
|
11 |
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
language:
|
3 |
- bn
|
4 |
- en
|
5 |
+
license: cc-by-4.0
|
6 |
+
library_name: peft
|
7 |
+
datasets:
|
8 |
+
- iamshnoo/alpaca-cleaned-bengali
|
9 |
+
base_model: meta-llama/Llama-2-13b-hf
|
10 |
---
|
11 |
This represents the PEFT weights only. The base model is LLaMA 2. Instruction finetuning was done using 4 bit QLoRA on a single A100 GPU with the PEFT config as given below. The dataset used for this instruction finetuning process is a translated version of the cleaned alpaca dataset (translated using NLLB-1.3B).
|
12 |
|